CODEWITHSUNDEEP
pythonmachine-learning
ROSA LILI
ROSA LILI

Reputation: 141

TypeError: reduction operation 'argmax' not allowed for this dtype

I don't actually know what is wrong with my code. Could anyone help?

from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import KFold, cross_val_score
from sklearn.metrics import confusion_matrix,precision_recall_curve,auc,roc_auc_score,roc_curve,recall_score,classification_report

def printing_Kfold_scores(x_train_data,y_train_data):
    fold = KFold(len(y_train_data),5,shuffle=False) 

    # Different C parameters
    c_param_range = [0.01,0.1,1,10,100]

    results_table = pd.DataFrame(index = range(len(c_param_range),2), columns = ['C_parameter','Mean recall score'])
    results_table['C_parameter'] = c_param_range

    # the k-fold will give 2 lists: train_indices = indices[0], test_indices = indices[1]
    j = 0
    for c_param in c_param_range:
        print('-------------------------------------------')
        print('C parameter: ', c_param)
        print('-------------------------------------------')
        print('')

        recall_accs = []
        for iteration, indices in enumerate(fold,start=1):

            # Call the logistic regression model with a certain C parameter
            lr = LogisticRegression(C = c_param, penalty = 'l1')

            # Use the training data to fit the model. In this case, we use the portion of the fold to train the model
            # with indices[0]. We then predict on the portion assigned as the 'test cross validation' with indices[1]
            lr.fit(x_train_data.iloc[indices[0],:],y_train_data.iloc[indices[0],:].values.ravel())

            # Predict values using the test indices in the training data
            y_pred_undersample = lr.predict(x_train_data.iloc[indices[1],:].values)

            # Calculate the recall score and append it to a list for recall scores representing the current c_parameter
            recall_acc = recall_score(y_train_data.iloc[indices[1],:].values,y_pred_undersample)
            recall_accs.append(recall_acc)
            print('Iteration ', iteration,': recall score = ', recall_acc)

        # The mean value of those recall scores is the metric we want to save and get hold of.
        results_table.ix[j,'Mean recall score'] = np.mean(recall_accs)
        j += 1
        print('')
        print('Mean recall score ', np.mean(recall_accs))
        print('')

    best_c = results_table.loc[results_table['Mean recall score'].idxmax()]['C_parameter']

    # Finally, we can check which C parameter is the best amongst the chosen.
    print('*********************************************************************************')
    print('Best model to choose from cross validation is with C parameter = ', best_c)
    print('*********************************************************************************')

    return best_c

best_c = printing_Kfold_scores(X_train_undersample,y_train_undersample)

Upvotes: 7

Views: 15353

Answers (2)

刘川枫
刘川枫

Reputation: 399

the last answer is right but might should change

results_table['Mean recall score']=results_table['Mean recall'].astype('float64')

to

results_table['Mean recall score']=results_table['Mean recall score'].astype('float64')

Upvotes: 1

user9648304
user9648304

Reputation: 69

I know where the problem is: the dtype of results_table['Mean recall score'] is object! the idxmax not allowed for the "object"

you should change it to float, here is my solution:

results_table['Mean recall score']=results_table['Mean recall'].astype('float64')

best_c = results_table.loc[results_table['Mean recall score'].idxmax()]['C_parameter']

And this will work!

Upvotes: 6

Related Questions